PandasAI

What it does

PandasAI is an open-source Python library for business analysts, data scientists, and engineers. Users provide data such as CSV files or dataframes and ask questions in natural language. The library interprets queries and translates them into Python code or SQL queries to interact with the data, returning results through the Python interface.

The workflow is to install the library, configure a language model, load data, and call the chat interface; users can also work with multiple dataframes. Documented functions include generating charts, addressing missing values, and feature generation. The library is MIT-licensed except for its enterprise directory. It is not the hosted Annie dashboard described on the company website. Use requires a Python environment and a configured LLM; the documented example uses an OpenAI API key, so model access and any associated charges are separate considerations. The repository lists Python 3.8 through 3.11 as requirements.

What it can do

• Natural-language data querying
• Translate natural-language questions into Python code and SQL queries
• Generate graphs and charts
• Clean datasets by addressing missing values
• Generate features to enhance data quality
• Query multiple dataframes

Works with

• PostgreSQL
• MySQL
• BigQuery
• Databricks
• Snowflake
• LiteLLM
• OpenAI

Before you choose

• Requires a Python environment and a configured LLM; external model access or usage charges may apply and are not included in the library license.
• The repository lists support for Python 3.8 through 3.11; operating-system compatibility is not specified in the vendor documentation.
• MIT license excludes the pandasai/ee directory, which has separate licensing; enterprise offerings are distinct.
• Review generated code and results, and limit the data and execution permissions available to the configured model.

Listed under

• Data
• Ask your data
• AI data analyst
• Business intelligence
• Dashboards
• Natural language
• Open source
• Text-to-SQL

Get started

Configure a language model and load your data.

1. Install pandasai using pip or Poetry; install the LiteLLM integration if needed.
2. Configure an LLM; the documented example configures LiteLLM with an OpenAI model and API key.
3. Load data in Python and submit a question using the dataframe chat interface.

Library is available under the MIT expat license except for pandasai/ee; separate enterprise licensing may apply. The website's Annie subscription prices are for a distinct hosted dashboard and are not attributed to this library.

PandasAI is free to use. See their pricing page ↗

Sources for this overview

Product pages, documentation, and pricing checked 1 Nov 2026. Each source supports part of the overview; availability and prices can change.

• Introduction to PandasAI - PandasAI ↗docs.pandas-ai.com
• GitHub - sinaptik-ai/pandas-ai: Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG. · GitHub ↗github.com
• PandasAI - AI Dashboard for Business Intelligence ↗pandas-ai.com

Company website

docs.pandas-ai.com: product, pricing and policy pages

YC directory mirror

Batch and company name

Human review

Checked by a person

manual_review

Last checked 1 Nov 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.